Fid膿lis = faithful, loyal, true, trustworthy, dependable
Note: Preview images are generated without the use of LORAs.
About
This model is aimed for photorealism but at the same time versatile and flexible with its generations. It is mostly geared towards generating muscular men with defined muscles so it might not be as good with other body types. Also, while this model is mainly created for male-oriented NSFW stuff, it can still be used to generate SFW images..
My Settings
These are just some examples of the settings I usually use and it's not really a hard requirement so you're free to experiment and see which setting works best for you:
Sampling Method: DPM++ 2M Karras or DPM++ SDE Karras
Sampling Steps: 25 - 50
Hires. fix: On
Upscaler: ESRGAN 4x+ or 4x_NMKD-Siax_200k or 8x_NMKD-Superscale_150000_G (if you have it)
Hires Steps: I usually put it at 0 so it'll be the same as Sampling Steps
Denoising Strength: 0.25 - 0.35
Upscale: 1.5 - 2
CFG Scale: 4 - 8
Clip Skip: 1-2
Extra Tips
Try to keep the prompts short and concise. No need to fill up the prompts with unnecessary wording that does the same thing like high detail, ultra detail, absurdres, hires, photorealistic, hyperrealistic, etc. Keep it simple.
ADetailer is key if you want to get good looking faces. If you're generating a close up shot or portrait, most of the time you won't need it. But if its a full body or far shot, ADetailer is absolutely necessary unless you wanna get distorted or blurry looking faces.
Hires fix is highly recommended, especially for far and wide shots where a lot of details are getting lost. And if you're using LORAs, it is mandatory to use it because without it, the output might look a little blurry and overcooked.
Use negative embeddings instead if writing paragraphs of words into the negative prompts. Avoid using too much at once. Here are some examples of the ones I usually use:
CyberRealistic Negative (Personal fav, seems to work best for me)
BadDream & UnrealisticDream (Less realistic but more creative result)
realisticvision-negative-embedding (Pretty good as well)
Description
v5.0
What's new:
Overall improvement
Rebuild using v4.0 as the base model
Added some loras and change the merge used to give it more versatility
Easier to generate 'beefier' characters
Can generate basic sex positions but its still SD1.5 so its still pretty unreliable
FAQ
Comments (17)
I am thrilled that SD 1.5 is still getting love. Not all of us can convert to the likes of Flux when we don't even have room for XL or Pony yet.
Yeah lol. My PC is pretty basic so I can only do SD1.5 stuff for now.. 馃様
@Kairen92聽I still prefer SD1.5 anyway. I don't like the way XL looks and I can't ever get Pony to work properly. Forget Flux. And my PC is too full for any of them anyway.
Please put this new version of HomoFidelis on Tensor to. I use Tensor a lot more than Civit.
I'll see what I can do..
@Kairen92聽Thank you.
OMG!!! I want to say your new version 5.0 of HomoFidelis is really awesome !
Aww thank you so much, I really appreciate that! :)
Love your model. My favourite 1.5 one. 鉂わ笍
Thank you so much!! :)
I wish you were updating for sdxl
I wish I was too, but I don't have a pc thats good enough to train sdxl/pony models. Maybe someday I'll buy a new graphics card.. :')
Please make this model available again with the civitai generator. It was the only good homoerotic model available for sd 1.5.
I'm sorry, but I can't do anything about it. Civitai took it off because they only allow 1 checkpoint from me on the generator. I already emailed them asking to let it stay on but they said no.
I love this. I was using it with the civitai generator, but it's no longer an option. :(
I'm sorry, I tried but Civitai would not let me put more than one model on the generator.. 馃様馃檹
These are so hot mate! You have a real talent!